Home Knowledge Base the Smart Optimization & Learning

the Smart Optimization & Learning

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Can LLMs Beat Classical Hyperparameter Optimization Algorithms?

Computer Science > Machine Learning [Submitted on 25 Mar 2026 (v1), last revised 17 Apr 2026 (this version, v5)] Title:Can LLMs Beat Classical Hyperparameter Optimization Algorithms?

Hacker News 1d ago

Scaling Decision-Focused Learning to Large Problems with Lagrangian Decomposition

arXiv:2606.08797v1 Announce Type: new Abstract: Decision-focused learning has shown great promise for addressing predict-then-optimize problems, particularly in the presence of under-specified models. However, its practical deployment is often hindered by high computational costs and limited scalability, as it requires solving a constrained optimization problem for each training instance at every iteration. To address these challenges, we propose a novel framework that incorporates...

arXiv CS 1d ago

PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models

Announce Type: new Abstract: Despite the pivotal role of numerical reasoning as the cornerstone of mathematical capabilities in large language models (LLMs) across applications, few benchmarks evaluate LLMs by integrating numerical processing and mathematical reasoning, hindering the interpretability of failures in math tasks. We introduce PyraMathBench, a comprehensive hierarchical benchmark with 32,505 questions derived from 7,404 math word problems, spanning 4 key cognitive aspects, 14...

arXiv CS 7d ago

Human-Like Neural Nets by Catapulting

Human-like Neural Nets by Catapulting Speculative proposal to create artificial neural nets with human-like performance by high-learning-rate/regularization training of overparameterized NNs to trigger catapulting/grokking. Over-parameterization as a route to true generalization would resolve many outstanding mysteries of artificial versus natural intelligence. There are many mysteries about deep learning and human intelligence, but we could describe the biggest anomaly this way: why are...

Hacker News 3d ago

Smart Transportation Without Neurons -- Fair Metro Network Expansion with Tabular Reinforcement Learning

arXiv:2606.04167v1 Announce Type: new Abstract: We tackle the Metro Network Expansion Problem (MNEP), a subset of the Transport Network Design Problem (TNDP), which focuses on expanding metro systems to satisfy travel demand. Traditional methods rely on exact and heuristic approaches that require expert-defined constraints to reduce the search space. Recently, deep reinforcement learning (Deep RL) has emerged due to its effectiveness in complex sequential decision-making processes-it...

arXiv CS 6d ago

Whole-genome duplication shaped cell-type evolution in the vertebrate brain

Abstract The complex brains of vertebrates have more cell types than those of their closest relatives. Whole-genome duplications (WGDs) occurred during early vertebrate evolution1, but it is unclear whether the duplicated genes (ohnologues) facilitated cell-type evolution. Here using brain single-cell transcriptomes from five chordates—human2, mouse3, lizard4, lamprey5 and amphioxus—we report that many cell-type families with conserved core transcription factors in vertebrates do not show...

Nature 20h ago

Gemma 4 QAT models: Optimizing compression for mobile and laptop efficiency

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency Since releasing Gemma 4 two months ago, we've been continuously working to expand its capabilities. First, we introduced Multi-Token Prediction (MTP) to accelerate inference, and just a couple of days ago, we released a 12B model to bridge the gap between our E4B and 26B MOE models. Today, we are releasing new checkpoints optimized with Quantization-Aware Training (QAT) to make Gemma 4 even more efficient, so...

Hacker News 5d ago

Food industries embrace AI sensors to improve efficiencies

Food industries embrace AI sensors to improve efficiencies Lisa Lock Scientific Editor Andrew Zinin Lead Editor Food waste is a nagging problem that weighs heavily on global food production, distribution and sales industries—but an emerging generation of AI sensors is providing a raft of fresh solutions. The embrace of AI in food industries has been swift, which is why Flinders University researchers have worked with an international research team to build the first comprehensive overview of...

Phys.org 7d ago

A Reliable Self-Organized Distributed Complex Network for Communication of Smart Agents

arXiv:2503.07702v3 Announce Type: replace Abstract: Collaboration among distributed agents is fundamental to many complex systems, particularly in communication networks where connectivity must be maintained under energy constraints. In this study, we utilize intelligent agents (nodes) trained through reinforcement learning techniques to establish connections with their neighbors, ultimately leading to the emergence of a large-scale communication cluster. Notably, there is no centralized...

arXiv CS 5d ago